Senior Software Engineer, AI Systems & ML Infrastructure
I build the engineering layer that turns models into reliable products. My focus is inference, evaluation, agents, and the observability and cost controls around them.
8+ years across backend services, distributed systems, and production reliability. Now I focus on inference, evaluation, agents, and the observability and cost controls that turn models into dependable products.
Senior engineer operating at staff scope. Open to Staff-level AI systems and ML infrastructure roles.
The platform story
Each project is a slice of a single production AI platform, from data and features to training, evaluation, inference, agents, safety, and the observability around them.
Data
Contracts, quality, lineage
Features
Governed feature store
Training
Distributed post-training
Evaluation
Eval + regression gates
Inference
Multi-provider gateway
Agents
Governed tool use
Safety
Policy + moderation
Observability
AI SRE, golden signals
Real-time
Streaming risk scoring
Projects
Inference & Reliability
In progressRouting, caching, rate limiting, and failover across model providers, plus an AI SRE control plane for health, cost, and incident response.
Training & Post-Training
PlannedOrchestrates distributed fine-tuning / post-training jobs with reproducible pipelines, checkpointing, and evaluation gates before promotion.
Agents & Retrieval
PlannedGoverned retrieval and tool use with human approval for risky actions. It helps triage incidents without acting unsafely on its own.
Evaluation & Data
PlannedA closed-loop evaluation and data flywheel with a governed feature store powering ranking and recommendations, with lineage from raw data to features to models.
Trust & Safety
PlannedA multimodal content-understanding pipeline for policy enforcement and moderation with auditable, explainable decisions and human review for edge cases.
Streaming & Real-Time
PlannedReal-time feature computation, scoring, and alerting over event streams, with backpressure handling and replayable pipelines from edge to cloud.
Focus
Writing
Designing an LLM gateway you can actually operate
Routing, caching, quotas, and failover across providers, and why the control plane matters as much as the data plane.
Evaluation as a CI gate, not a spreadsheet
Golden sets, regression thresholds, and a data flywheel that keeps model quality from silently drifting.
Agents that ask permission
Permission-aware retrieval, guarded tools, and human approval for building agentic systems that are safe to audit.
AI SRE: golden signals for model-serving systems
Latency, cost, error, and quality as first-class signals, and what a degraded mode should look like.
Topics are listed honestly as planned until the essays are published.